A novel approach to robot vision using a hexagonal grid and spiking neural networks

D Kerr, SA Coleman, TM McGinnity, Qingxiang Wu, M. Clogenson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Many robots use range data to obtain an almost 3-dimensional description of their environment. Feature driven segmentation of range images has been primarily used for 3D object recognition, and hence the accuracy of the detected features is a prominent issue. Inspired by the structure and behaviour of the human visual system, we present an approach to feature extraction in range data using spiking neural networks and a biologically plausible hexagonal pixel arrangement. Standard digital images are converted into a hexagonal pixel representation and then processed using a spiking neural network with hexagonal shaped receptive fields; this approach is a step towards developing a robotic eye that closely mimics the human eye. The performance is compared with receptive fields implemented on standard rectangular images. Results illustrate that, using hexagonally shaped receptive fields, performance is improved over standard rectangular shaped receptive fields.
LanguageEnglish
Title of host publicationUnknown Host Publication
Number of pages7
DOIs
Publication statusPublished - 30 Jul 2012
EventThe 2012 International Joint Conference on Neural Networks (IJCNN) - Brisbane, Australia
Duration: 30 Jul 2012 → …

Conference

ConferenceThe 2012 International Joint Conference on Neural Networks (IJCNN)
Period30/07/12 → …

Fingerprint

Computer vision
Neural networks
Pixels
Object recognition
Feature extraction
Robotics
Robots

Cite this

@inproceedings{17f5084ae96c49838c40a23f9c542543,
title = "A novel approach to robot vision using a hexagonal grid and spiking neural networks",
abstract = "Many robots use range data to obtain an almost 3-dimensional description of their environment. Feature driven segmentation of range images has been primarily used for 3D object recognition, and hence the accuracy of the detected features is a prominent issue. Inspired by the structure and behaviour of the human visual system, we present an approach to feature extraction in range data using spiking neural networks and a biologically plausible hexagonal pixel arrangement. Standard digital images are converted into a hexagonal pixel representation and then processed using a spiking neural network with hexagonal shaped receptive fields; this approach is a step towards developing a robotic eye that closely mimics the human eye. The performance is compared with receptive fields implemented on standard rectangular images. Results illustrate that, using hexagonally shaped receptive fields, performance is improved over standard rectangular shaped receptive fields.",
author = "D Kerr and SA Coleman and TM McGinnity and Qingxiang Wu and M. Clogenson",
year = "2012",
month = "7",
day = "30",
doi = "10.1109/IJCNN.2012.6252591",
language = "English",
isbn = "978-1-4673-1488-6",
booktitle = "Unknown Host Publication",

}

Kerr, D, Coleman, SA, McGinnity, TM, Wu, Q & Clogenson, M 2012, A novel approach to robot vision using a hexagonal grid and spiking neural networks. in Unknown Host Publication. The 2012 International Joint Conference on Neural Networks (IJCNN), 30/07/12. https://doi.org/10.1109/IJCNN.2012.6252591

A novel approach to robot vision using a hexagonal grid and spiking neural networks. / Kerr, D; Coleman, SA; McGinnity, TM; Wu, Qingxiang; Clogenson, M.

Unknown Host Publication. 2012.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A novel approach to robot vision using a hexagonal grid and spiking neural networks

AU - Kerr, D

AU - Coleman, SA

AU - McGinnity, TM

AU - Wu, Qingxiang

AU - Clogenson, M.

PY - 2012/7/30

Y1 - 2012/7/30

N2 - Many robots use range data to obtain an almost 3-dimensional description of their environment. Feature driven segmentation of range images has been primarily used for 3D object recognition, and hence the accuracy of the detected features is a prominent issue. Inspired by the structure and behaviour of the human visual system, we present an approach to feature extraction in range data using spiking neural networks and a biologically plausible hexagonal pixel arrangement. Standard digital images are converted into a hexagonal pixel representation and then processed using a spiking neural network with hexagonal shaped receptive fields; this approach is a step towards developing a robotic eye that closely mimics the human eye. The performance is compared with receptive fields implemented on standard rectangular images. Results illustrate that, using hexagonally shaped receptive fields, performance is improved over standard rectangular shaped receptive fields.

AB - Many robots use range data to obtain an almost 3-dimensional description of their environment. Feature driven segmentation of range images has been primarily used for 3D object recognition, and hence the accuracy of the detected features is a prominent issue. Inspired by the structure and behaviour of the human visual system, we present an approach to feature extraction in range data using spiking neural networks and a biologically plausible hexagonal pixel arrangement. Standard digital images are converted into a hexagonal pixel representation and then processed using a spiking neural network with hexagonal shaped receptive fields; this approach is a step towards developing a robotic eye that closely mimics the human eye. The performance is compared with receptive fields implemented on standard rectangular images. Results illustrate that, using hexagonally shaped receptive fields, performance is improved over standard rectangular shaped receptive fields.

U2 - 10.1109/IJCNN.2012.6252591

DO - 10.1109/IJCNN.2012.6252591

M3 - Conference contribution

SN - 978-1-4673-1488-6

BT - Unknown Host Publication

ER -